arXiv AI
Jul 8
Base Models Know How to Reason, Thinking Models Learn When
arXiv:2510. 07364v4 Announce Type: replace Abstract: What do thinking language models learn during training that their base models lack?
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv AI
Jul 8
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
arXiv:2607. 06565v1 Announce Type: cross Abstract: Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single backbone, but their text-3D interaction remains largely implicit.
arXiv AI
Jul 8
Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
arXiv:2605. 13974v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood.
arXiv AI
Jul 8
Akashic: A Low-Overhead LLM Inference Service with MemAttention
arXiv:2607. 05708v1 Announce Type: new Abstract: Recent LLM-based agent systems continuously accumulate context across multi-turn interactions, tool invocations, and cross-session workflows.
arXiv Machine Learning
Jul 8
Federated Physics-Grounded Reinforcement Learning for Distributed Stability Control in Smart Grids
arXiv:2607. 05553v1 Announce Type: new Abstract: Transient stability control in smart grids requires rapid post-fault damping of generator frequency and rotor angle deviations to prevent cascading failures.
arXiv Machine Learning
Jul 8
Deep Reinforcement Learning for Dynamic Battery Management of Autonomous Order Pickers
arXiv:2607. 05683v1 Announce Type: new Abstract: Battery charging of Autonomous Mobile Robots (AMRs) in warehouses is a critical operational challenge that heavily impacts both order processing times and throughput.
arXiv Machine Learning
Jul 8
Multimodal Molecular Representation Learning with Graph Neural Networks, Deep & Cross Networks, and SMILES Embeddings
arXiv:2607. 05736v1 Announce Type: new Abstract: Molecular property prediction often relies on isolated data modalities, where continuous 3D graph neural networks (GNNs) struggle to efficiently capture long-range topological dependencies and exact macroscopic heuristics.
Hugging Face Trending Papers
Jul 7
FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games
We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's minimalist 2D fighting game Footsies, it isolates the cyclic, non-transitive strategic interactions of fighting game neutral play while remaining simple enough for efficient analysis.
Hugging Face Trending Papers
Jul 7
Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement
Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations. In particular, flow matching-based VLA models have shown remarkable success due to their capability to generate precise and smooth action sequences and capture multimodal distributions.
Hugging Face Trending Papers
Jul 7
High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control
Image outpainting extends an image beyond its original borders, requiring seamless style integration and globally coherent scene completion. Building on the success of diffusion models, recent methods have achieved substantial improvements in visual quality.
Hugging Face Trending Papers
Jul 7
CurateEvo: Data-Curation Evolving for Agentic Post-Training
Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existing agentic post-training pipelines often treat data curation as a fixed preprocessing step, focusing mainly on data augmentation while neglecting filtering, refinement, and adaptation to downstream failures.
Hugging Face Trending Papers
Jul 7
AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models
Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization.
arXiv AI
Jul 7
Human-like Object Grouping in Self-supervised Vision Transformers
arXiv:2603. 13994v2 Announce Type: replace-cross Abstract: Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties.
arXiv AI
Jul 7
From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving
arXiv:2607. 02574v1 Announce Type: cross Abstract: The key-value (KV) cache has become a first-order memory object in LLM serving rather than a temporary per-request tensor.
arXiv AI
Jul 7
Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI
arXiv:2606. 16533v3 Announce Type: replace Abstract: We introduce \textbf{Kairos}, a regret-aware native world-action model stack for Physical AI.
arXiv AI
Jul 7
Rethinking On-Policy Self-Distillation for Thinking Models
arXiv:2607. 05184v1 Announce Type: new Abstract: Self-distillation is a promising recipe for self-improvement in language models.
arXiv AI
Jul 7
PEEK: Predictive Queue-Informed KV Cache Management for LLM Serving
arXiv:2607. 02525v1 Announce Type: cross Abstract: We present PEEK, a lightweight scheduling and eviction framework for both online (streaming) and offline (batch) LLM serving; this paper focuses on the online regime.
arXiv AI
Jul 7
Embodied Operators and Benchmarking: Toward Reusable and Deployable Embodied Intelligence Systems
arXiv:2607. 03283v1 Announce Type: new Abstract: Embodied intelligence systems require not only end-to-end policy models, but also reusable functional modules that transform multimodal observations, robot states, human demonstrations, and task contexts into structured representations, decisions, trajectories, control references, and system services.
arXiv AI
Jul 7
Gemma 4 Technical Report
arXiv:2607. 02770v1 Announce Type: cross Abstract: We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family.
arXiv AI
Jul 7
Scalable Maximal Frequent Episode Mining with Desbordante
arXiv:2607. 03188v1 Announce Type: cross Abstract: Episode mining aims to extract subsequences of events that possess certain distinctive properties and constitute facts valuable to the user.